English

DeepTopPush: Simple and Scalable Method for Accuracy at the Top

Machine Learning 2023-03-28 v2 Optimization and Control Machine Learning

Abstract

Accuracy at the top is a special class of binary classification problems where the performance is evaluated only on a small number of relevant (top) samples. Applications include information retrieval systems or processes with manual (expensive) postprocessing. This leads to minimizing the number of irrelevant samples above a threshold. We consider classifiers in the form of an arbitrary (deep) network and propose a new method DeepTopPush for minimizing the loss function at the top. Since the threshold depends on all samples, the problem is non-decomposable. We modify the stochastic gradient descent to handle the non-decomposability in an end-to-end training manner and propose a way to estimate the threshold only from values on the current minibatch and one delayed value. We demonstrate the excellent performance of DeepTopPush on visual recognition datasets and two real-world applications. The first one selects a small number of molecules for further drug testing. The second one uses real malware data, where we detected 46\% malware at an extremely low false alarm rate of 10510^{-5}.

Keywords

Cite

@article{arxiv.2006.12293,
  title  = {DeepTopPush: Simple and Scalable Method for Accuracy at the Top},
  author = {Václav Mácha and Lukáš Adam and Václav Šmídl},
  journal= {arXiv preprint arXiv:2006.12293},
  year   = {2023}
}
R2 v1 2026-06-23T16:31:20.965Z